BETA
Smaller Qwen2-VL — single-GPU vision model. Cheap self-hosted alternative to GPT-4o-mini for vision tasks.
Qwen2-VL-7B is a multimodal AI model from Qwen. It costs $0.300 per million input tokens and $0.300 per million output tokens (blended $0.300/M), with a 32K-token context window.
Qwen2-VL-7B costs $0.300 per million input tokens and $0.300 per million output tokens, for a blended reference rate of $0.300 per million tokens.
Qwen2-VL-7B supports up to 32K tokens of context (32,000 tokens).
Qwen2-VL-7B is well suited to Single-GPU vision, Open weights and Document understanding.
Qwen2-VL-7B is developed and served by Qwen. It was released in Aug 2024.